CN116238524A - Driving behavior discrimination method and system based on high-precision map and vehicle history track - Google Patents
Driving behavior discrimination method and system based on high-precision map and vehicle history track Download PDFInfo
- Publication number
- CN116238524A CN116238524A CN202310301421.7A CN202310301421A CN116238524A CN 116238524 A CN116238524 A CN 116238524A CN 202310301421 A CN202310301421 A CN 202310301421A CN 116238524 A CN116238524 A CN 116238524A
- Authority
- CN
- China
- Prior art keywords
- lane
- obstacle
- driving behavior
- vehicle
- frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012850 discrimination method Methods 0.000 title claims description 9
- 230000008859 change Effects 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 12
- 238000013500 data storage Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 2
- 230000006399 behavior Effects 0.000 description 68
- 239000000284 extract Substances 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4044—Direction of movement, e.g. backwards
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2556/00—Input parameters relating to data
- B60W2556/40—High definition maps
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The utility model discloses a driving behavior judging method and system based on high-precision map and vehicle history track, combine high-precision map and vehicle history track to the driving behavior of vehicle, under the state that can not involve hardware data, initiatively draw real-time lane information of vehicle, it takes place to trade the way behavior to judge the vehicle through the change of lane number, assist the distance between initial and current lane simultaneously and judge the direction of trading the way, can avoid lane number to take place frequent change under the lane merging sight, and can judge the complete cycle that the vehicle traded the way through the lane position that the vehicle is located, finally realize the continuous and accurate judgement to the vehicle driving behavior.
Description
Technical Field
The application relates to the technical field of automatic driving prediction, in particular to a driving behavior judging method and system based on a high-precision map and a vehicle history track.
Background
According to the existing scheme, the historical track points of the vehicle are searched, the course difference between every two track points in the historical track points is calculated, when the course difference exceeds a preset value, the points are used as starting points of track changing of the vehicle, track points with the first angular speed change in the follow-up track points are found out to be used as track changing end points according to the angular speed of the starting points, all track points between the track changing starting points and the track changing end points are track changing sequences, and if the track changing sequences can be found in the historical track points of the vehicle, the track changing behavior of the vehicle is judged. However, the existing schemes have the defects that only one lane change behavior of the vehicle can be judged, accurate judgment (such as left lane change and right lane change) cannot be performed on the behavior, and judgment is excessively dependent on the accuracy of the vehicle track, such as failure in judgment caused by small jump of the course/angular speed of the vehicle track, which is why the judgment of the behavior based on the sensor data is impossible at present, and the data of the sensor itself has certain disturbance, so that accurate behavior judgment cannot be realized.
Disclosure of Invention
In order to solve the technical problems, the embodiment of the application provides a driving behavior judging method and system based on a high-precision map and a vehicle history track.
The first aspect of the embodiments of the present application provides a driving behavior discriminating method based on a high-precision map and a vehicle history track, which may include the following steps:
step S1, acquiring a high-precision map and a historical track of an obstacle to form an obstacle characteristic sequence, wherein the obstacle comprises all vehicles in a target environment;
s2, based on the obtained obstacle characteristic sequence, taking a starting frame as a reference, obtaining driving behavior characteristics of each frame relative to the starting frame, wherein the driving behavior characteristics comprise heading characteristics and distance characteristics;
step S3, acquiring a characteristic sequence of the current vehicle, and judging the driving behavior of the current obstacle based on the driving behavior characteristics;
and step S4, after the driving behavior obtained in the step S3 is stored in the behavior sequence, updating the current frame into a starting frame, and repeating the steps S2-S3 until the characteristic sequence of the obstacle is traversed, so as to form the continuous behavior of the obstacle.
Further, the obstacle characteristic sequence in the step S1 includes a position, a heading, a lane number, a lane width, an angle difference between an obstacle orientation and a lane, and an area of each obstacle at each moment.
Further, step S2 traverses each frame of the obstacle feature sequence and compares the initial frames to obtain heading features and distance features between the two frames; the heading characteristic comprises a heading deviation angle, and the distance characteristic comprises a center line distance of a lane where the heading characteristic is located and a center line distance of a vehicle of a current frame and the lane where the heading characteristic is located.
Further, the center line distance of the lane is the distance between a first projection point formed by projecting the obstacle from the position of the current frame to the lane center line of the starting frame and a second projection point formed by projecting the first projection point to the lane center line of the current frame.
Further, the distance between the vehicle of the current frame and the center line of the lane is the distance between a third projection point formed by projecting the obstacle from the position of the current frame to the lane of the current frame and the center line of the lane of the current frame.
Further, in the step S3, it is determined whether reverse driving is performed and whether a steering operation is performed based on the heading of the obstacle and the angle difference between the heading of the lane.
Further, whether to run reversely is determined based on whether the difference between the heading of the obstacle and the heading angle of the lane reaches a preset reverse running angle threshold.
Further, in the step S3, it is determined whether a lane change operation is performed based on the lane number information and the center line distance of the lane.
Further, based on whether the lane number of the current frame and the lane number of the start frame are changed, whether the absolute value of the center line distance between the lane of the current frame and the lane of the start frame exceeds 1/2 of the lane width of the current frame (to accurately judge the start time of the behavior), and whether to change lanes left and right (left, right, negative) is judged according to the positive and negative of the center line distance between the lane of the current frame and the lane of the start frame so as to judge the lane change of the barrier and the lane change direction.
Further, regarding the determination of the straight-going behavior, consider an ordinary road or intersection where the obstacle is currently located:
if the initial frame is positioned on the common road, the lane number is consistent with the lane number of the current frame, and the absolute value of the course deviation between the initial frame and the current frame is smaller than the straight-going threshold value of the common road;
if the initial frame is positioned on the common road, the current frame is positioned at the intersection, and the absolute value of the heading deviation between the initial frame and the current frame is smaller than the straight-going threshold value of the common road;
if the initial frame is positioned at the intersection, the current frame is positioned on the common road, and the absolute value of the heading deviation between the initial frame and the current frame is smaller than the intersection straight-going threshold value.
A second aspect of the embodiments of the present application provides a driving behavior discrimination system based on a high-precision map and a vehicle history track, including:
the characteristic sequence module is used for forming an obstacle characteristic sequence based on the high-precision map and the historical track of the obstacle, wherein the obstacle comprises all vehicles in a target environment, and the obstacle characteristic sequence comprises the position, the course and the lane information of each obstacle at each moment;
the traversing module is used for acquiring driving behavior characteristics of each frame relative to a starting frame based on the acquired obstacle characteristic sequence by taking the first frame as the starting frame, wherein the driving behavior characteristics comprise heading characteristics and distance characteristics;
the driving behavior module is used for screening the characteristic sequence of the current obstacle and the driving behavior characteristics thereof to judge the driving behavior of the current obstacle, updating the current frame into a starting frame after the driving behavior contained in the current frame is judged successfully, and traversing the current frame by the traversing module again;
and the behavior data storage module is used for storing the output data of the driving behavior module to form continuous behavior data of the obstacle.
Further, the traversing module traverses each frame of the obstacle feature sequence and compares the initial frames to obtain heading features and distance features between the two frames; the heading characteristic comprises a heading deviation angle, and the distance characteristic comprises a center line distance of a lane where the heading characteristic is located and a center line distance of a vehicle of a current frame and the lane where the heading characteristic is located.
Further, the driving behavior module determines whether reverse driving is achieved and whether steering operation exists based on the heading and lane orientation angle difference of the obstacle when determining the driving behavior, and determines whether lane changing operation exists based on lane number information and the center line distance of the lane.
The method has the advantages that the method combines the high-precision map with the driving behavior of the vehicle by the vehicle history track, actively extracts the real-time lane information (lane number/lane width) of the vehicle under the condition that hardware data can not be involved, accurately judges the lane change behavior of the vehicle through the change of the lane number, simultaneously assists the distance between the initial lane and the current lane to judge the lane change direction (left/right), can avoid frequent change of the lane number under the lane merging scene, judges the complete period (starting time) of the lane change of the vehicle through the position of the lane where the vehicle is located, and finally realizes continuous and accurate judgment of the driving behavior of the vehicle.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a driving behavior discrimination method provided in an embodiment of the present application;
fig. 2 is a logic block diagram of a driving behavior discrimination system provided in an embodiment of the present application.
Detailed Description
In order to make the application objects, features and advantages of the present application more obvious and understandable, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the embodiments described below are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The invention is further elucidated below in connection with the drawings and the specific embodiments.
In the description of the present application, it should be understood that the terms "upper," "lower," "top," "bottom," "inner," "outer," and the like indicate an orientation or a positional relationship based on that shown in the drawings, and are merely for convenience of description and simplification of the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present application.
The application provides a driving behavior judging method based on a high-precision map and a vehicle history track, which can comprise the following steps:
step S1, acquiring a high-precision map and a historical track (track map of a overlook angle) of an obstacle to form an obstacle characteristic sequence, wherein the obstacle comprises all vehicles in the surrounding environment including own vehicles, and the obstacle characteristic sequence at least comprises heading, track number and speed information of each obstacle at each moment.
As a specific example, the obstacle signature sequence includes the position, heading, lane number, lane width, angle difference between the direction of the obstacle and the lane, and the area where the intersection is mainly distinguished from the normal road.
And S2, based on the obtained obstacle characteristic sequence, taking a starting frame (a first frame) as a reference, obtaining driving behavior characteristics of each frame at the back relative to the starting frame, wherein the driving behavior characteristics comprise heading characteristics and distance characteristics, the heading characteristics comprise heading deviation angles, and the distance characteristics comprise the center line distance of a lane where the vehicle is located and the center line distance of the vehicle of the current frame and the lane where the vehicle is located.
As a specific example, the center line distance of the lane is not directly and simply defined as the lateral distance of two lanes, and the shape of the road needs to be considered, and the number of roads at the intersection changes, so that the center line distance is the distance between a first projection point formed by projecting the obstacle from the position of the current frame to the lane center line of the start frame and a second projection point formed by projecting the first projection point to the lane center line of the current frame.
The distance between the vehicle of the current frame and the center line of the lane is the distance between a third projection point formed by projecting the obstacle from the position of the current frame to the lane of the current frame and the center line of the lane of the current frame.
And step S3, acquiring a characteristic sequence of the current vehicle, and judging the driving behavior of the current obstacle based on the driving behavior characteristics.
As a specific embodiment, there are different determination modes for different driving behaviors:
and (3) driving in the reverse direction: and judging whether to run reversely or not based on whether the angle difference between the heading of the obstacle and the heading angle of the lane reaches a preset reverse running angle threshold value, and judging that the vehicle runs reversely as long as the reverse running angle threshold value is exceeded.
Steering and running: judging the absolute value of the heading deviation between the initial frame and the current frame to judge whether the vehicle exceeds a preset steering threshold, if the steering occurs, judging whether the vehicle reaches the U-shaped steering threshold in turn (namely, the whole turning amplitude of the general turning is 180 degrees, but the turning angle of the large vehicle is considered not to be excessively large, so that the turning angle is an action consisting of a plurality of frames, the threshold is set based on an empirical value), and if the vehicle does not turn in the U-shaped steering, judging the left-right steering (left-right positive-negative) according to the positive and negative directions of the heading deviation.
Lane change running: and judging whether the absolute value of the center line distance between the lane of the current frame and the lane of the starting frame exceeds 1/2 of the lane width of the current frame (to accurately judge the starting time of the behavior) based on whether the lane number of the current frame and the lane number of the starting frame are changed, if the lane number is changed and the absolute value exceeds 1/2 of the width, judging that the lane is changed, and judging whether the lane is changed (left, right, negative) according to the positive and negative of the center line distance between the lane of the current frame and the lane of the starting frame so as to judge the lane change of the barrier and the lane change direction. The lane change behavior is determined by skimming the change of the number of lanes when approaching an intersection and the condition of the line pressing of the vehicle, so that the lane and the traversing are required to meet the conditions to be determined.
And (3) running in a straight way: it is necessary to consider an ordinary road or intersection where an obstacle is currently located,
if the initial frame is positioned on the common road, the lane number is consistent with the lane number of the current frame, and the absolute value of the course deviation between the initial frame and the current frame is smaller than the straight-going threshold value of the common road;
if the initial frame is positioned on the common road, the current frame is positioned at the intersection, and the absolute value of the heading deviation between the initial frame and the current frame is smaller than the straight-going threshold value of the common road;
if the initial frame is positioned at the intersection, the current frame is positioned on the common road, and the absolute value of the heading deviation between the initial frame and the current frame is smaller than the intersection straight-going threshold value.
And S4, after the driving behavior obtained in the step S3 is stored in the behavior sequence, updating the corresponding frame into a starting frame, and repeating the steps S2-S3 until the characteristic sequence of the obstacle is traversed, so as to form the continuous behavior of the obstacle.
The method and the device are different from the lane recognition in the prior art, the method and the device combine a high-precision map with the history track of the vehicle to drive the vehicle, and can actively extract real-time lane information (lane number/lane width) of the vehicle under the condition that the motion prediction mode by taking the sensor as hardware is difficult to effectively complete the behavior prediction because the data can only be referenced and cannot be completely adopted in consideration of certain disturbance of the data of the sensor although the data of the sensor can be adopted, accurately judge the lane change direction (left/right) of the vehicle by the change of the lane number and simultaneously judge the lane number under the situation of lane combination by assisting with the distance between the initial lane and the current lane, and finally realize continuous and accurate judgment of the driving behavior of the vehicle by judging the complete period (starting time) of the lane change of the vehicle by taking the position of the vehicle.
The second aspect of the application provides a driving behavior discriminating system based on a high-precision map and a vehicle history track, which comprises a feature sequence module, a traversing module, a driving behavior module and a behavior data storage module.
As a specific embodiment, the feature sequence module forms an obstacle feature sequence based on the high-precision map and the historical track of the obstacle, wherein the obstacle comprises all vehicles in the target environment, including self vehicles, and the obstacle feature sequence comprises the position, the heading and the lane information of each obstacle at each moment, and specifically comprises the position, the heading, the lane number, the lane width, the angle difference between the direction of the obstacle and the lane, and the area (crossing/common road).
As a specific embodiment, the traversing module obtains driving behavior characteristics of each frame relative to a starting frame based on the obtained obstacle characteristic sequence and using the first frame as the starting frame, wherein the driving behavior characteristics comprise heading characteristics and distance characteristics.
As a preferred scheme, the traversing module traverses each frame of the obstacle feature sequence and compares the initial frames to obtain a heading feature and a distance feature between the two frames, wherein the heading feature comprises a heading deviation angle between the initial frame and the current frame, the distance feature comprises a distance between a center line of a lane of the current frame and a center line of the lane of the initial frame (a point A is obtained by projecting a vehicle position of the current frame to the center line of the lane of the initial frame, a point B is obtained by projecting the point A to the center line of the lane of the current frame, the distance of AB is the center line distance between the lane of the current frame and the lane of the initial frame), and a distance between a vehicle of the current frame and the lane of the current frame (a point C is obtained by projecting the position of the current frame to the lane of the current frame, and the distance between the current frame and the point C is the center line distance between the current frame and the lane of the current frame).
As a specific embodiment, the driving behavior module screens the characteristic sequence of the current obstacle and the driving behavior characteristics thereof to judge the driving behavior of the current obstacle, updates the current frame into the initial frame after the driving behavior contained in the current frame is judged successfully, and traverses the current frame by the traversing module again;
the driving behavior module determines whether reverse driving is achieved and whether steering operation exists based on the heading of the obstacle and the angle difference of the lane orientation when determining the driving behavior, and determines whether lane changing operation exists based on lane number information and the center line distance of the lane where the driving behavior module is located.
As a specific embodiment, the driving behavior module is provided with a reverse running determination unit, a lane change determination unit, a steering determination unit, and a straight running determination unit.
As a preferable mode, the reverse travel determination unit outputs the result by determining whether or not the difference between the obstacle course and the lane orientation angle reaches a preset reverse travel angle threshold value, and if the threshold value is exceeded, the reverse travel is determined.
As a preferable scheme, the lane change judging unit judges whether the lane number corresponding to the lane of the current frame and the lane number corresponding to the lane of the initial frame are changed, judges whether the absolute value of the distance between the center line of the lane of the current frame and the center line of the lane of the initial frame exceeds 1/2 of the width of the lane where the current frame is located (to accurately judge the initial time of the behavior), and judges whether to change lanes left and right according to the positive and negative of the center line distance between the lane of the current frame and the lane of the initial frame (for example, the difference corresponding to the lane change to the left is positive and the difference corresponding to the lane change to the right is negative).
As a preferable mode, the steering determination unit determines whether the vehicle exceeds a preset steering threshold by determining an absolute value of a heading deviation between a start frame and a current frame, if the absolute value exceeds the preset steering threshold, determines whether the vehicle is steered, and then sequentially determines whether the preset U-shaped steering threshold is reached (the action corresponding to the threshold is turning around), if the vehicle is not U-shaped steering, determines left-right steering (for example, a difference value corresponding to left steering is positive and a difference value corresponding to right steering is negative) according to the positive and negative of the heading deviation.
As a preferable mode, the straight-ahead determination unit makes a determination by the heading deviation, but considers a scene of an intersection or a normal road (since the place where the entire driving scene is located is fixed, it is possible to quickly locate whether the current obstacle is at the intersection or the normal road based on the surrounding environment). The following determination may be considered straight:
the initial frame is positioned on an ordinary road, the lane number of the initial frame is consistent with that of the current frame, and the absolute value of the course deviation between the initial frame and the current frame is smaller than the ordinary road straight-going threshold;
the initial frame is positioned on a common road, the current frame is positioned at an intersection, and the absolute value of the heading deviation between the initial frame and the current frame is smaller than the straight-going threshold value of the common road;
the initial frame is positioned at the crossing, the current frame is positioned on the common road, and the absolute value of the heading deviation between the initial frame and the current frame is smaller than the crossing straight-going threshold value.
As a specific embodiment, the behavior data storage module forms continuous behavior data of the obstacle by storing output data of the driving behavior module.
The system extracts real-time lane information (lane number/lane width) of the vehicle from the historical data, can accurately judge lane change behavior of the vehicle through the change of the lane number, is assisted with the judgment of lane change direction (left/right) from the initial distance between the lane number and the current lane, can avoid frequent change of the lane number under the lane merging scene, judges the complete cycle (starting time) of lane change of the vehicle through the lane position of the vehicle, can train out a network input historical track sequence and high-precision map information of the vehicle through deep learning to judge the behavior of the vehicle, and performs intention recognition, so that the accuracy of behavior intention recognition in the driving process of the vehicle at the back is ensured.
The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to the specific details of the above embodiments, and various equivalent changes (such as number, shape, position, etc.) may be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and these equivalent changes all belong to the protection of the present invention.
Claims (10)
1. A driving behavior discriminating method based on a high-precision map and a vehicle history track is characterized in that: the method comprises the following steps:
step S1, acquiring a high-precision map and a historical track of an obstacle to form an obstacle characteristic sequence, wherein the obstacle comprises all vehicles in a target environment;
s2, based on the obtained obstacle characteristic sequence, taking a starting frame as a reference, obtaining driving behavior characteristics of each frame relative to the starting frame, wherein the driving behavior characteristics comprise heading characteristics and distance characteristics;
step S3, acquiring a characteristic sequence of the current vehicle, and judging the driving behavior of the current obstacle based on the driving behavior characteristics;
and step S4, after the driving behavior obtained in the step S3 is stored in the behavior sequence, updating the current frame into a starting frame, and repeating the steps S2-S3 until the characteristic sequence of the obstacle is traversed, so as to form the continuous behavior of the obstacle.
2. The driving behavior discrimination method based on the high-definition map and the vehicle history trajectory according to claim 1, characterized in that: the obstacle characteristic sequence in the step S1 comprises the position, the course, the number of the lane where each obstacle is located, the width of the lane where each obstacle is located, the angle difference between the direction of the obstacle and the lane where each obstacle is located and the area where each obstacle is located at each moment.
3. The driving behavior discrimination method based on the high-definition map and the vehicle history trajectory according to claim 1, characterized in that: step S2, traversing each frame of the obstacle characteristic sequence, and comparing the initial frames to obtain heading characteristics and distance characteristics between the two frames; the heading characteristic comprises a heading deviation angle, and the distance characteristic comprises a center line distance of a lane where the heading characteristic is located and a center line distance of a vehicle of a current frame and the lane where the heading characteristic is located.
4. The driving behavior discrimination method based on a high-definition map and a vehicle history trajectory according to claim 3, characterized in that: the center line distance of the lane is the distance between a first projection point formed by projecting the obstacle from the position of the current frame to the lane center line of the starting frame and a second projection point formed by projecting the first projection point to the lane center line of the current frame.
5. The driving behavior discrimination method based on a high-definition map and a vehicle history trajectory according to claim 4, characterized in that: the distance between the vehicle of the current frame and the center line of the lane is the distance between a third projection point formed by projecting the obstacle from the position of the current frame to the lane of the current frame and the center line of the lane of the current frame.
6. The driving behavior discrimination method based on the high-definition map and the vehicle history trajectory according to claim 1, characterized in that: in the step S3, it is determined whether reverse driving is performed and whether a steering operation is performed based on the heading of the obstacle and the angle difference between the lane orientations.
7. The driving behavior discrimination method based on the high-definition map and the vehicle history trajectory according to claim 6, characterized in that: and in the step S3, judging whether a lane change operation exists or not based on the lane number information and the center line distance of the lane.
8. A driving behavior discriminating system based on a high-precision map and a vehicle history track is characterized in that: comprising the following steps:
the characteristic sequence module is used for forming an obstacle characteristic sequence based on the high-precision map and the historical track of the obstacle, wherein the obstacle comprises all vehicles in a target environment, and the obstacle characteristic sequence comprises the position, the course and the lane information of each obstacle at each moment;
the traversing module is used for acquiring driving behavior characteristics of each frame relative to a starting frame based on the acquired obstacle characteristic sequence by taking the first frame as the starting frame, wherein the driving behavior characteristics comprise heading characteristics and distance characteristics;
the driving behavior module is used for screening the characteristic sequence of the current obstacle and the driving behavior characteristics thereof to judge the driving behavior of the current obstacle, updating the current frame into a starting frame after the driving behavior contained in the current frame is judged successfully, and traversing the current frame by the traversing module again;
and the behavior data storage module is used for storing the output data of the driving behavior module to form continuous behavior data of the obstacle.
9. The driving behavior discrimination system based on a high-precision map and a vehicle history trajectory according to claim 8, wherein: the traversing module traverses each frame of the obstacle characteristic sequence and compares the initial frames to acquire heading characteristics and distance characteristics between the two frames; the heading characteristic comprises a heading deviation angle, and the distance characteristic comprises a center line distance of a lane where the heading characteristic is located and a center line distance of a vehicle of a current frame and the lane where the heading characteristic is located.
10. The driving behavior discrimination system based on a high-precision map and a vehicle history trajectory according to claim 8, wherein: the driving behavior module judges whether reverse driving is achieved or not and whether steering operation exists or not based on the heading of the obstacle and the angle difference of the lane orientation when judging the driving behavior, and judges whether lane changing operation exists or not based on lane number information and the center line distance of the lane where the lane is located.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310301421.7A CN116238524B (en) | 2023-03-27 | 2023-03-27 | Driving behavior discrimination method and system based on high-precision map and vehicle history track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310301421.7A CN116238524B (en) | 2023-03-27 | 2023-03-27 | Driving behavior discrimination method and system based on high-precision map and vehicle history track |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116238524A true CN116238524A (en) | 2023-06-09 |
| CN116238524B CN116238524B (en) | 2024-02-09 |
Family
ID=86631355
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310301421.7A Active CN116238524B (en) | 2023-03-27 | 2023-03-27 | Driving behavior discrimination method and system based on high-precision map and vehicle history track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116238524B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003296899A (en) * | 2002-03-29 | 2003-10-17 | Toyota Central Res & Dev Lab Inc | Preceding vehicle determining device |
| KR20040009371A (en) * | 2002-07-23 | 2004-01-31 | 현대자동차주식회사 | Traffic line detection controlling method of vehicle |
| CN105206090A (en) * | 2015-10-13 | 2015-12-30 | 厦门星辰天羽汽车设计有限公司 | Vehicle positioning method |
| CN107563310A (en) * | 2017-08-16 | 2018-01-09 | 电子科技大学 | A kind of lane change detection method violating the regulations |
| CN109145860A (en) * | 2018-09-04 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Lane line tracking and device |
| CN112819864A (en) * | 2021-04-16 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Driving state detection method and device and storage medium |
| CN113504782A (en) * | 2021-09-09 | 2021-10-15 | 北京智行者科技有限公司 | Obstacle collision prevention method, device and system and moving tool |
| CN113771881A (en) * | 2021-10-19 | 2021-12-10 | 中国第一汽车股份有限公司 | Vehicle lane change control method and device, electronic equipment and storage medium |
| CN114771572A (en) * | 2022-05-10 | 2022-07-22 | 中国第一汽车股份有限公司 | Automatic driving track prediction method, device, equipment and storage medium |
| CN114879659A (en) * | 2022-03-31 | 2022-08-09 | 广州文远知行科技有限公司 | Method, device and equipment for identifying retrograde obstacle and storage medium |
| CN114889638A (en) * | 2022-04-22 | 2022-08-12 | 武汉路特斯汽车有限公司 | Trajectory prediction method and system in automatic driving system |
| CN115195790A (en) * | 2022-09-15 | 2022-10-18 | 毫末智行科技有限公司 | Method and device for predicting vehicle track, electronic equipment and storage medium |
-
2023
- 2023-03-27 CN CN202310301421.7A patent/CN116238524B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003296899A (en) * | 2002-03-29 | 2003-10-17 | Toyota Central Res & Dev Lab Inc | Preceding vehicle determining device |
| KR20040009371A (en) * | 2002-07-23 | 2004-01-31 | 현대자동차주식회사 | Traffic line detection controlling method of vehicle |
| CN105206090A (en) * | 2015-10-13 | 2015-12-30 | 厦门星辰天羽汽车设计有限公司 | Vehicle positioning method |
| CN107563310A (en) * | 2017-08-16 | 2018-01-09 | 电子科技大学 | A kind of lane change detection method violating the regulations |
| CN109145860A (en) * | 2018-09-04 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Lane line tracking and device |
| CN112819864A (en) * | 2021-04-16 | 2021-05-18 | 腾讯科技（深圳）有限公司 | Driving state detection method and device and storage medium |
| CN113504782A (en) * | 2021-09-09 | 2021-10-15 | 北京智行者科技有限公司 | Obstacle collision prevention method, device and system and moving tool |
| CN113771881A (en) * | 2021-10-19 | 2021-12-10 | 中国第一汽车股份有限公司 | Vehicle lane change control method and device, electronic equipment and storage medium |
| CN114879659A (en) * | 2022-03-31 | 2022-08-09 | 广州文远知行科技有限公司 | Method, device and equipment for identifying retrograde obstacle and storage medium |
| CN114889638A (en) * | 2022-04-22 | 2022-08-12 | 武汉路特斯汽车有限公司 | Trajectory prediction method and system in automatic driving system |
| CN114771572A (en) * | 2022-05-10 | 2022-07-22 | 中国第一汽车股份有限公司 | Automatic driving track prediction method, device, equipment and storage medium |
| CN115195790A (en) * | 2022-09-15 | 2022-10-18 | 毫末智行科技有限公司 | Method and device for predicting vehicle track, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116238524B (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109583151B (en) | Method and device for predicting running track of vehicle | |
| CN108230731B (en) | Parking lot navigation system and method | |
| CN110962843B (en) | Automatic parking control decision method and system | |
| JP3690283B2 (en) | Lane tracking control device | |
| CN113267199B (en) | Method and device for planning driving track | |
| CN110531661B (en) | Automatic following control method, device and equipment for vehicle | |
| CN109801508A (en) | The motion profile prediction technique and device of barrier at crossing | |
| JP2019156174A (en) | Vehicle control device, vehicle, vehicle control method, and program | |
| CN110834630A (en) | Vehicle driving control method and device, vehicle and storage medium | |
| US20220169280A1 (en) | Method and Device for Multi-Sensor Data Fusion For Automated and Autonomous Vehicles | |
| CN110667581B (en) | Automatic lane change control system and automatic lane change control method for vehicle | |
| CN106184232A (en) | A kind of lane departure warning control method based on driver visual angle | |
| CN105501288A (en) | Steering assist control apparatus and steering assist control method | |
| CN111959498A (en) | Vertical parking method and device for automatically driving vehicle and vehicle | |
| CN112141114A (en) | Narrow passage auxiliary system and method | |
| CN115230719A (en) | Driving track planning method and device | |
| Friji et al. | A dqn-based autonomous car-following framework using rgb-d frames | |
| CN116238524B (en) | Driving behavior discrimination method and system based on high-precision map and vehicle history track | |
| JP4007355B2 (en) | Lane tracking control device | |
| Gackstatter et al. | Stable road lane model based on clothoids | |
| CN117227714A (en) | Control method and system for turning avoidance of automatic driving vehicle | |
| DE102020202476A1 (en) | Method and device for estimating at least one object state of a moving object in the vicinity of a vehicle | |
| CN115230743B (en) | Method, system, electronic device and storage medium for predicting obstacle trajectory | |
| Bruno et al. | Advanced driver assistance system based on automated routines for the benefit of human faults correction in robotics vehicles | |
| JP5906987B2 (en) | Predicted trajectory guidance system, method and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |